© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60627
    Prev
    Next
    INDEX
    Explanations

    legal citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĮº
    -0.08
    зна
    -0.07
    .desktop
    -0.07
    aye
    -0.07
    veri
    -0.07
    é¢ł
    -0.07
     Casc
    -0.07
    vern
    -0.07
    人æ°ijæĶ¿åºľ
    -0.07
    æŁ¥
    -0.07
    POSITIVE LOGITS
    oger
    0.07
    رÙĪض
    0.06
    off
    0.06
    书è¯Ħ
    0.06
    og
    0.06
    elang
    0.06
    åħ³æ³¨åĴĮ
    0.06
    oulder
    0.06
    andes
    0.06
    ATS
    0.06
    Activations Density 0.043%

    No Known Activations